Trispectral Analysis of Voiced Sounds Defective Audition and Tracheotomisian Cases

This paper presents the cepstral and trispectral analysis of a speech signal produced by normal men, men with defective audition (deaf, deep deaf) and others affected by tracheotomy, the trispectral analysis based on parametric methods (Autoregressive AR) using the fourth order cumulant. These analyses are used to detect and compare the pitches and the formants of corresponding voiced sounds (vowel \a\, \i\ and \u\). The first results appear promising, since- it seems after several experimentsthere is no deformation of the spectrum as one could have supposed it at the beginning, however these pathologies influenced the two characteristics: The defective audition influences to the formants contrary to the tracheotomy, which influences the fundamental frequency (pitch).

Authors:



References:
[1] J. W. A. Fackrell and S. McLaughlin, "H.O.S. of speech signals" IEE
Coll. Tech. In Speech Signal Proc., London, June 1994.
[2] H. P. Rathy, S. Prasad and S. D. Joshi , "Conditions for third order
stationarity and ergodicity of a harmonic random process" IEEE Trans.
On signal Proc., vol. 42, N┬░ 1, pp. 222-224, Jan. 1994.
[3] J. Mendel , "Tutorial on higher- order statistics" Proc. IEEE, vol 79,
N┬░3, pp. 277-303, March 1991.
[4] V. Chandran and S. L. Elgar, " A general procedure for derivation of
principal domains of higher-order spectra", IEEE Trans. On Signal
Proc., vol. 42, N┬░1, pp. 229-233, Jan. 1994.
[5] J. W. A Fackrell etal, "Non linearity detection for condition monitoring
using h.o.s" Internal rep., Dept of Elect. and Elect. Eng., University of
Edimburgh, Scotland, pp. 519-528, July 1996.
[6] J. Markel and A. Gray, « Linear prediction of speech » , Springer-
Verlag, 1976.
[7] Pediatric Otolaryngology: Learning Center - Tracheotomy
http://www.pediatric-ent.com/learning/surgeries/tracheotomy.htm